Estimating morning and evening commute period O3 concentration in Taiwan using a fine spatial-temporal resolution ensemble mixed spatial model with Geo-AI technology

Chin-Yu Hsu; Ruei-Qin Lee; Pei-Yi Wong; Shih-Chun Candice Lung; Yu-Cheng Chen; Pau-Chung Chen; Gary Adamkiewicz; Chih-Da Wu

doi:10.1016/j.jenvman.2023.119725

Estimating morning and evening commute period O₃ concentration in Taiwan using a fine spatial-temporal resolution ensemble mixed spatial model with Geo-AI technology

J Environ Manage. 2024 Feb:351:119725. doi: 10.1016/j.jenvman.2023.119725. Epub 2023 Dec 7.

Authors

Chin-Yu Hsu¹, Ruei-Qin Lee², Pei-Yi Wong³, Shih-Chun Candice Lung⁴, Yu-Cheng Chen⁵, Pau-Chung Chen⁶, Gary Adamkiewicz⁷, Chih-Da Wu⁸

Affiliations

¹ Department of Safety, Health and Environmental Engineering, Ming Chi University of Technology, New Taipei, Taiwan; Center for Environmental Sustainability and Human Health, Ming Chi University of Technology, New Taipei, Taiwan.
² Department of Geomatics, National Cheng Kung University, Tainan, Taiwan.
³ Department of Environmental and Occupational Health, National Cheng Kung University, Tainan, Taiwan.
⁴ Research Center for Environmental Changes, Academia Sinica, Taipei, Taiwan; Department of Atmospheric Sciences, National Taiwan University, Taipei, Taiwan.
⁵ National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan.
⁶ National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan; Institute of Environmental and Occupational Health Sciences, National Taiwan University College of Public Health, Taipei, Taiwan; Department of Public Health, National Taiwan University College of Public Health, Taipei, Taiwan; Department of Environmental and Occupational Medicine, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan.
⁷ Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
⁸ Department of Geomatics, National Cheng Kung University, Tainan, Taiwan; National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan; Innovation and Development Center of Sustainable Agriculture, National Chung Hsing University, Tainan, Taiwan. Electronic address: chidawu@mail.ncku.edu.tw.

PMID: 38064987
DOI: 10.1016/j.jenvman.2023.119725

Abstract

Elevated levels of ground-level ozone (O₃) can have harmful effects on health. While previous studies have focused mainly on daily averages and daytime patterns, it's crucial to consider the effects of air pollution during daily commutes, as this can significantly contribute to overall exposure. This study is also the first to employ an ensemble mixed spatial model (EMSM) that integrates multiple machine learning algorithms and predictor variables selected using Shapley Additive exExplanations (SHAP) values to predict spatial-temporal fluctuations in O₃ concentrations across the entire island of Taiwan. We utilized geospatial-artificial intelligence (Geo-AI), incorporating kriging, land use regression (LUR), machine learning (random forest (RF), categorical boosting (CatBoost), gradient boosting (GBM), extreme gradient boosting (XGBoost), and light gradient boosting (LightGBM)), and ensemble learning techniques to develop ensemble mixed spatial models (EMSMs) for morning and evening commute periods. The EMSMs were used to estimate long-term spatiotemporal variations of O₃ levels, accounting for in-situ measurements, meteorological factors, geospatial predictors, and social and seasonal influences over a 26-year period. Compared to conventional LUR-based approaches, the EMSMs improved performance by 58% for both commute periods, with high explanatory power and an adjusted R² of 0.91. Internal and external validation procedures and verification of O₃ concentrations at the upper percentile ranges (in 1%, 5%, 10%, 15%, 20%, and 25%) and other conditions (including rain, no rain, weekday, weekend, festival, and no festival) have demonstrated that the models are stable and free from overfitting issues. Estimation maps were generated to examine changes in O₃ levels before and during the implementation of COVID-19 restrictions. These findings provide accurate variations of O₃ levels in commute period with high spatiotemporal resolution of daily and 50m * 50m grid, which can support control pollution efforts and aid in epidemiological studies.

Keywords: Commute periods; Ensemble mixed spatial model (EMSM); Geospatial artificial intelligence; Land use regression; O(3).

MeSH terms

Air Pollutants* / analysis
Air Pollution* / analysis
Artificial Intelligence
Environmental Monitoring / methods
Particulate Matter / analysis
Taiwan

Substances

Air Pollutants
Particulate Matter